Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Strategies & Market Trends : TA-Quotes Plus -- Ignore unavailable to you. Want to Upgrade?

To: ftth who wrote (4399)	6/14/1998 5:17:00 PM
From: Spots	Respond to of 11149

>> I just don't buy it that separate IDE drives give any improvement. Well, don't take my word for it (doesn't seem likely); try it and see. Will eat my words if separate drives don't help. It's true that the IDE controller is single-threaded, but that doesn't make the whole OS single threaded. Lot's happens outside the controller. Spots PS. When the controller can transfer from its cache, it doesn't make a lot of difference whether the controller is single threaded or not.

To: ftth who wrote (4399)	6/14/1998 5:37:00 PM
From: Bob Jagow	Read Replies (1) \| Respond to of 11149

Dave, Of course "ATA (whether Ultra-DMA or not) is a single-threaded I/O interface, and can only execute 1 request at a time." That's why I have SCSI. IDE is still faster on two disks "because their heads are in place for subsequent reads" -- would you agree that physical seeks have higher latency than the difference between whether "the thread scheduler [has to] execute [threads] in (multiplexed) series, which has higher overhead than linear execution on a single processor" bj